Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 8115
    Prev
    Next
    INDEX
    Explanations

    mentions of institutional positions and processes related to fellowships or academic appointments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCulture
    -0.64
    endsection
    -0.53
    UVWXYZ
    -0.52
     rospy
    -0.51
    rager
    -0.49
     minOccurs
    -0.48
     Disconnect
    -0.48
     disconnecting
    -0.46
    存于互联网档案馆
    -0.46
    |}{$
    -0.46
    POSITIVE LOGITS
     application
    1.96
     applications
    1.94
     applicants
    1.92
     Applications
    1.80
     Application
    1.80
     applicant
    1.74
    application
    1.73
    Applications
    1.72
    Application
    1.71
     Applicants
    1.65
    Activations Density 0.562%

    No Known Activations